Early prediction of diagnostic-related groups and estimation of hospital cost by processing clinical notes

Abstract As healthcare providers receive fixed amounts of reimbursement for given services under DRG (Diagnosis-Related Groups) payment, DRG codes are valuable for cost monitoring and resource allocation. However, coding is typically performed retrospectively post-discharge. We seek to predict DRGs...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jinghui Liu, Daniel Capurro, Anthony Nguyen, Karin Verspoor
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/529a6a6b713b432a95fc348393aca21f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:529a6a6b713b432a95fc348393aca21f
record_format	dspace
spelling	oai:doaj.org-article:529a6a6b713b432a95fc348393aca21f2021-12-02T18:18:42ZEarly prediction of diagnostic-related groups and estimation of hospital cost by processing clinical notes10.1038/s41746-021-00474-92398-6352https://doaj.org/article/529a6a6b713b432a95fc348393aca21f2021-07-01T00:00:00Zhttps://doi.org/10.1038/s41746-021-00474-9https://doaj.org/toc/2398-6352Abstract As healthcare providers receive fixed amounts of reimbursement for given services under DRG (Diagnosis-Related Groups) payment, DRG codes are valuable for cost monitoring and resource allocation. However, coding is typically performed retrospectively post-discharge. We seek to predict DRGs and DRG-based case mix index (CMI) at early inpatient admission using routine clinical text to estimate hospital cost in an acute setting. We examined a deep learning-based natural language processing (NLP) model to automatically predict per-episode DRGs and corresponding cost-reflecting weights on two cohorts (paid under Medicare Severity (MS) DRG or All Patient Refined (APR) DRG), without human coding efforts. It achieved macro-averaged area under the receiver operating characteristic curve (AUC) scores of 0·871 (SD 0·011) on MS-DRG and 0·884 (0·003) on APR-DRG in fivefold cross-validation experiments on the first day of ICU admission. When extended to simulated patient populations to estimate average cost-reflecting weights, the model increased its accuracy over time and obtained absolute CMI error of 2·40 (1·07%) and 12·79% (2·31%), respectively on the first day. As the model could adapt to variations in admission time, cohort size, and requires no extra manual coding efforts, it shows potential to help estimating costs for active patients to support better operational decision-making in hospitals.Jinghui LiuDaniel CapurroAnthony NguyenKarin VerspoorNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 4, Iss 1, Pp 1-8 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Jinghui Liu Daniel Capurro Anthony Nguyen Karin Verspoor Early prediction of diagnostic-related groups and estimation of hospital cost by processing clinical notes
description	Abstract As healthcare providers receive fixed amounts of reimbursement for given services under DRG (Diagnosis-Related Groups) payment, DRG codes are valuable for cost monitoring and resource allocation. However, coding is typically performed retrospectively post-discharge. We seek to predict DRGs and DRG-based case mix index (CMI) at early inpatient admission using routine clinical text to estimate hospital cost in an acute setting. We examined a deep learning-based natural language processing (NLP) model to automatically predict per-episode DRGs and corresponding cost-reflecting weights on two cohorts (paid under Medicare Severity (MS) DRG or All Patient Refined (APR) DRG), without human coding efforts. It achieved macro-averaged area under the receiver operating characteristic curve (AUC) scores of 0·871 (SD 0·011) on MS-DRG and 0·884 (0·003) on APR-DRG in fivefold cross-validation experiments on the first day of ICU admission. When extended to simulated patient populations to estimate average cost-reflecting weights, the model increased its accuracy over time and obtained absolute CMI error of 2·40 (1·07%) and 12·79% (2·31%), respectively on the first day. As the model could adapt to variations in admission time, cohort size, and requires no extra manual coding efforts, it shows potential to help estimating costs for active patients to support better operational decision-making in hospitals.
format	article
author	Jinghui Liu Daniel Capurro Anthony Nguyen Karin Verspoor
author_facet	Jinghui Liu Daniel Capurro Anthony Nguyen Karin Verspoor
author_sort	Jinghui Liu
title	Early prediction of diagnostic-related groups and estimation of hospital cost by processing clinical notes
title_short	Early prediction of diagnostic-related groups and estimation of hospital cost by processing clinical notes
title_full	Early prediction of diagnostic-related groups and estimation of hospital cost by processing clinical notes
title_fullStr	Early prediction of diagnostic-related groups and estimation of hospital cost by processing clinical notes
title_full_unstemmed	Early prediction of diagnostic-related groups and estimation of hospital cost by processing clinical notes
title_sort	early prediction of diagnostic-related groups and estimation of hospital cost by processing clinical notes
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/529a6a6b713b432a95fc348393aca21f
work_keys_str_mv	AT jinghuiliu earlypredictionofdiagnosticrelatedgroupsandestimationofhospitalcostbyprocessingclinicalnotes AT danielcapurro earlypredictionofdiagnosticrelatedgroupsandestimationofhospitalcostbyprocessingclinicalnotes AT anthonynguyen earlypredictionofdiagnosticrelatedgroupsandestimationofhospitalcostbyprocessingclinicalnotes AT karinverspoor earlypredictionofdiagnosticrelatedgroupsandestimationofhospitalcostbyprocessingclinicalnotes
_version_	1718378213488459776

Early prediction of diagnostic-related groups and estimation of hospital cost by processing clinical notes

Ejemplares similares